OnCo
ideasIdea

Pre-agreed update rules so an MCED test is not obsolete when its trial reads out

A cancer blood test improves every year, but a ten-year trial tests the old version. Regulators and sponsors could agree in advance how updates are validated and carried into the result.

FDA's Predetermined Change Control Plan for AI devices offers a model. Propose an MCED-specific plan: the classifier may be updated on banked baseline samples under locked-test-set rules, each version must be shown non-inferior on a sequestered set, and the primary analysis uses the enrolment version with a pre-specified sensitivity analysis re-scoring banked plasma.

Hypothesis
With banked plasma re-scored by an updated classifier under pre-agreed rules, estimated effect sizes fall within 10% of those from the enrolment version, allowing an updated test to inherit trial evidence.
Rationale
Without this, each improved assay restarts the evidence clock, which is why the field keeps launching new observational studies instead of finishing randomised ones.
What would test it
Apply retrospectively in NHS-Galleri or PATHFINDER 2 banked plasma; publish agreement between classifier versions.
Maturity
speculative
Who has to act
regulator
Cost to try
Small (under $1M)
Years to first evidence
3
Bottlenecks it attacks

Connected

9top

Pages like this

not linked directly; found by shared links